Journal
NEURAL COMPUTING & APPLICATIONS
Volume 34, Issue 1, Pages 333-348Publisher
SPRINGER LONDON LTD
DOI: 10.1007/s00521-021-06372-1
Keywords
Breast cancer; Inception V3; Inception V4; Inception MV4; Deep convolutional neural network; Thermography
Categories
Funding
- Deanship of Scientific Research at King Khalid University [R.G.P.1/219/42]
Ask authors/readers for more resources
Breast thermography supported by deep convolutional neural networks is expected to contribute significantly to early detection of breast cancer. Different recent deep learning methods were investigated for identifying breast disorders. Results showed that Inception V4 and MV4 had high accuracy with color images, while Inception V3 outperformed V4 and MV4 with grayscale images. Increasing the number of layers may not necessarily improve the performance.
Breast cancer is one of the most significant causes of death for women around the world. Breast thermography supported by deep convolutional neural networks is expected to contribute significantly to early detection and facilitate treatment at an early stage. The goal of this study is to investigate the behavior of different recent deep learning methods for identifying breast disorders. To evaluate our proposal, we built classifiers based on deep convolutional neural networks modelling inception V3, inception V4, and a modified version of the latter called inception MV4. MV4 was introduced to maintain the computational cost across all layers by making the resultant number of features and the number of pixel positions equal. DMR database was used for these deep learning models in classifying thermal images of healthy and sick patients. A set of epochs 3-30 were used in conjunction with learning rates 1 x 10(-3), 1 x 10(-4) and 1 x 10(-5), Minibatch 10 and different optimization methods. The training results showed that inception V4 and MV4 with color images, a learning rate of 1 x 10(-4), and SGDM optimization method, reached very high accuracy, verified through several experimental repetitions. With grayscale images, inception V3 outperforms V4 and MV4 by a considerable accuracy margin, for any optimization methods. In fact, the inception V3 (grayscale) performance is almost comparable to inception V4 and MV4 (color) performance but only after 20-30 epochs. inception MV4 achieved 7% faster classification response time compared to V4. The use of MV4 model is found to contribute to saving energy consumed and fluidity in arithmetic operations for the graphic processor. The results also indicate that increasing the number of layers may not necessarily be useful in improving the performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available